Security audit
Glossary Builder
Security checks across malware telemetry and agentic risk
Overview
This skill only guides an agent to create localization glossaries and does not request unusual access or background behavior.
Review any product copy or terminology you provide because it may contain confidential product language, but the skill itself is narrowly scoped to formatting and improving localization glossaries.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.